Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.83
    GenerationType
    -0.65
    DataAnnotations
    -0.61
     tehd
    -0.59
    ClientRect
    -0.59
    aleza
    -0.59
     Gaulle
    -0.59
    väg
    -0.58
    yntaxException
    -0.58
     Lorentz
    -0.57
    POSITIVE LOGITS
     happy
    3.70
     Happy
    3.19
    happy
    3.15
     HAPPY
    3.03
    Happy
    2.97
    HAPPY
    2.77
     happier
    2.64
     happiest
    2.42
     happiness
    2.39
     feliz
    2.33
    Act Density 0.043%

    No Known Activations